Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to warranties and legal disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    warranty and claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ropriate
    -0.46
    EndContext
    -0.45
     san
    -0.42
     Sun
    -0.42
     Tab
    -0.42
    LayoutPanel
    -0.41
     Elephant
    -0.41
     SUN
    -0.40
     Ego
    -0.40
     Klu
    -0.40
    POSITIVE LOGITS
     WARRANTIES
    0.62
    ceğine
    0.58
     AssemblyCompany
    0.58
     garansi
    0.58
     garantie
    0.54
     nicio
    0.53
     guarantee
    0.53
     guarantees
    0.52
     warranty
    0.52
     Garantie
    0.52
    Act Density 0.021%

    No Known Activations